Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 196.88 +/- 24.38
+      value: 188.92 +/- 43.23
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211476473515f261630c0066d1509ea3e34cd044415776b2f7fd89d5387caf91
+oid sha256:994cd6f0876a00dc2f94de5aff405f237cb05ad819c469df9c4946fa298c1425
 size 147030

results.json

@@ -1 +1 @@
-{"mean_reward": 196.88246251374045, "std_reward": 24.378736464146257, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-29T02:43:15.174629"}
+{"mean_reward": 188.92078459741757, "std_reward": 43.228746302059875, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-29T03:02:30.995762"}